INDEX

Explanations

key technical terms and functions related to device or system performance

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Mood

-0.14

 icons

-0.14

 Turk

-0.13

_TLS

-0.13

 Ð¿ÑĢÐ¾Ðº

-0.13

dock

-0.13

 Icons

-0.12

lige

-0.12

Tcp

-0.12

POSITIVE LOGITS

 channel

0.32

 Channel

0.30

channel

0.27

Channel

0.25

 channels

0.24

.Channel

0.24

 Channels

0.24

_Channel

0.24

 CHANNEL

0.24

-channel

0.24

Activations Density 0.001%

key technical terms and functions related to device or system performance

No Comments

No Known Activations